AI in Manufacturing Course

Lesson 1 • Data as the Foundation of AI

Explains why data quality and volume drive AI performance. Introduces sensor data, operational data, and structured versus unstructured data types.

Lesson 2 • Key AI Technologies and Techniques

Surveys supervised, unsupervised, and reinforcement learning methods. Grounds each technique in manufacturing use cases to build applied intuition.

Lesson 3 • What AI Means for Manufacturing

Defines AI, machine learning, and deep learning in plain terms. Connects each concept to tangible manufacturing scenarios like defect detection and demand forecasting.

Lesson 1 • Data Preprocessing and Feature Engineering

Teaches cleaning, normalisation, and transformation of raw manufacturing data. Directly prepares learners to produce model-ready datasets.

Lesson 2 • Data Governance and Security

Defines data ownership, access controls, and retention policies for industrial environments. Ensures AI projects comply with data privacy and security obligations.

Lesson 3 • Sensors and IoT in Production

Covers sensor types, placement strategies, and IoT connectivity protocols. Establishes how physical signals become digital data streams for AI consumption.

Lesson 1 • Building Predictive Maintenance Models

Guides model selection, training, and validation for equipment health prediction. Covers regression, classification, and anomaly detection approaches.

Lesson 2 • Maintenance Strategy Fundamentals

Contrasts reactive, preventive, and predictive maintenance approaches. Quantifies the business case for AI-driven predictive maintenance over traditional methods.

Lesson 3 • Failure Mode Analysis and Data Labelling

Applies failure mode and effects analysis to identify critical assets and failure signatures. Produces labelled datasets required for supervised predictive models.

Lesson 1 • Statistical and Hybrid AI Quality Models

Combines classical statistical methods with machine learning for process monitoring. Addresses multivariate quality control scenarios common in complex manufacturing.

Lesson 2 • Deploying and Validating Inspection Systems

Covers validation protocols, false positive management, and regulatory documentation for AI inspection systems. Ensures systems meet industry quality standards.

Lesson 3 • Computer Vision for Defect Detection

Teaches image acquisition, preprocessing, and convolutional neural network application for surface defect detection. Learners configure vision systems for production lines.

Lesson 1 • Inventory Optimisation Using AI

Applies reinforcement learning and optimisation algorithms to safety stock and reorder point decisions. Reduces carrying costs while maintaining service levels.

Lesson 2 • Supply Chain Risk and Disruption Management

Applies AI to identify, quantify, and mitigate supply chain risks and disruptions. Builds resilience through scenario modelling and early warning systems.

Lesson 3 • Production Scheduling and Sequencing

Uses AI search and optimisation methods to generate efficient production schedules. Addresses constraints such as machine capacity, changeover time, and due dates.

Lesson 1 • Continuous Improvement with Digital Twins

Embeds digital twins into continuous improvement cycles such as PDCA and Six Sigma. Demonstrates how simulation accelerates hypothesis testing and change validation.

Lesson 2 • AI-Driven Process Parameter Tuning

Applies reinforcement learning and Bayesian optimisation to tune process parameters in simulation before live deployment. Reduces trial-and-error on the production floor.

Lesson 3 • Process Optimisation Fundamentals

Introduces optimisation problem types and AI-based solvers applicable to manufacturing processes. Connects optimisation objectives to operational KPIs like throughput and yield.

Lesson 1 • Perception and Decision-Making in Robots

Covers sensor fusion, object recognition, and AI decision-making pipelines that enable robots to act in unstructured environments. Builds understanding of robot intelligence layers.

Lesson 2 • AI Robotics Landscape in Manufacturing

Maps the spectrum from fixed automation to fully autonomous robots and collaborative robots. Establishes selection criteria based on task complexity and human interaction needs.

Lesson 3 • Deploying and Governing Autonomous Systems

Covers commissioning, performance validation, and ongoing governance of autonomous manufacturing systems. Ensures accountability and safety compliance throughout the system lifecycle.

Lesson 1 • AI Governance Frameworks

Establishes policies, roles, and oversight mechanisms to ensure responsible AI use in manufacturing. Addresses model accountability, bias monitoring, and audit processes.

Lesson 2 • Measuring and Sustaining AI Value

Defines metrics to track ongoing AI value delivery and prevent model degradation. Embeds continuous monitoring into operational management routines.

Lesson 3 • Building an AI Business Case

Structures financial and strategic justification for AI investments in manufacturing. Covers ROI modelling, risk quantification, and executive communication techniques.